Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2927 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6433. Min Range: -7.6433
Max Act: 7.6433. Min Act: -0.1700
Data Index: 3009648 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6433. Min Range: -7.6433
Max Act: 7.5183. Min Act: -0.1700
Data Index: 685738 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6433. Min Range: -7.6433
Max Act: 7.5183. Min Act: -0.1700
Data Index: 3498766 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6433. Min Range: -7.6433
Max Act: 7.1745. Min Act: -0.1700
Data Index: 3566171 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6433. Min Range: -7.6433
Max Act: 7.0183. Min Act: -0.1700
Data Index: 1824211 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6433. Min Range: -7.6433
Max Act: 6.9245. Min Act: -0.1700
Data Index: 3259786 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6433. Min Range: -7.6433
Max Act: 6.9245. Min Act: -0.1700
Data Index: 5181433 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6433. Min Range: -7.6433
Max Act: 6.8933. Min Act: -0.1700
Data Index: 4983001 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6433. Min Range: -7.6433
Max Act: 6.8933. Min Act: -0.1700
Data Index: 8460663 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6433. Min Range: -7.6433
Max Act: 6.8933. Min Act: -0.1700
Data Index: 2533837 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6433. Min Range: -7.6433
Max Act: 6.8308. Min Act: -0.1700
Data Index: 623510 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6433. Min Range: -7.6433
Max Act: 6.8308. Min Act: -0.1700
Data Index: 8183324 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6433. Min Range: -7.6433
Max Act: 6.8308. Min Act: -0.1700
Data Index: 5820162 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6433. Min Range: -7.6433
Max Act: 6.7995. Min Act: -0.1700
Data Index: 5226043 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6433. Min Range: -7.6433
Max Act: 6.7995. Min Act: -0.1700
Data Index: 7488166 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6433. Min Range: -7.6433
Max Act: 6.7683. Min Act: -0.1700
Data Index: 5073888 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6433. Min Range: -7.6433
Max Act: 6.7370. Min Act: -0.1700
Data Index: 335096 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6433. Min Range: -7.6433
Max Act: 6.7370. Min Act: -0.1700
Data Index: 6786362 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6433. Min Range: -7.6433
Max Act: 6.7370. Min Act: -0.1700
Data Index: 2317275 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6433. Min Range: -7.6433
Max Act: 6.7370. Min Act: -0.1700
Data Index: 7354477 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #19